[PR #10675] convert: quantize from safetensors needs kv #13320

Closed
opened 2026-04-13 00:23:44 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/10675

State: closed
Merged: Yes


When creating a quantized model from safetensors we need the array KV values to be loaded.Changing this value to -1 loads the KV values on the returned layer to be used and saved during quantization.

**Original Pull Request:** https://github.com/ollama/ollama/pull/10675 **State:** closed **Merged:** Yes --- When creating a quantized model from safetensors we need the array KV values to be loaded.Changing this value to -1 loads the KV values on the returned layer to be used and saved during quantization.
GiteaMirror added the pull-request label 2026-04-13 00:23:44 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13320